Andreas Stöffelbauer

andreasskyscanner's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 23 hours ago

Miles v0.1: Production-Level Post-Training

Paper • 2609.08368 • Published 3 days ago • 50

upvoted a paper 3 days ago

One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation

Paper • 2608.25936 • Published 16 days ago • 13

upvoted a paper 4 days ago

Group Adaptive Clipping Policy Optimization

Paper • 2609.00444 • Published 11 days ago • 9

upvoted a paper 7 days ago

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published 8 days ago • 91

upvoted 2 papers 8 days ago

It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning

Paper • 2609.00638 • Published 10 days ago • 72

Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall

Paper • 2609.01532 • Published 10 days ago • 9

upvoted 2 papers 10 days ago

Evaluating the Hidden Costs of Personalization in Large Language Models

Paper • 2608.28833 • Published 14 days ago • 30

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published 11 days ago • 151

upvoted a paper 18 days ago

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

Paper • 2608.12875 • Published 29 days ago • 15

upvoted a paper 25 days ago

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 28 days ago • 170

upvoted a paper 27 days ago

DarwinX: Evolving Agent Harnesses Through Natural Selection

Paper • 2608.07545 • Published Jul 31 • 113

upvoted a paper 29 days ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 219

upvoted 2 papers about 1 month ago

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Paper • 2608.05000 • Published Aug 6 • 63

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published Jul 26 • 106

upvoted 3 papers about 2 months ago

NVIDIA-labs OO Agents: Native Python Object-Oriented Agents

Paper • 2607.20709 • Published Jul 22 • 36

Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness

Paper • 2607.19322 • Published Jul 21 • 11

Understanding Reasoning from Pretraining to Post-Training

Paper • 2607.16097 • Published Jul 17 • 30

upvoted 3 papers 2 months ago

Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing

Paper • 2607.07953 • Published Jul 8 • 16

Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models

Paper • 2607.05803 • Published Jul 7 • 11

LLM-as-a-Verifier: A General-Purpose Verification Framework

Paper • 2607.05391 • Published Jul 6 • 19